Loading...
Loading...
Found 141 Skills
Zero-ceremony inline execution for tasks completable in 3 or fewer file edits. No plan, no subagent, no research — just understand, do, commit, log. Use for "quick fix", "typo fix", "one-line change", "trivial fix", "rename this variable", "update this value", "fix this import". Do NOT use for tasks requiring research, planning, new dependencies, or more than 3 file edits — redirect to /quick instead.
Structured specification with explicit scope boundaries: user stories, acceptance criteria, out-of-scope definition, risks, and estimation. Positions before feature-design in the feature lifecycle pipeline. Use when: "write spec", "user stories", "define requirements", "scope this", "what should this do", "acceptance criteria", "define scope"
Generate blog post topic ideas through problem mining, gap analysis, and technology expansion. Use when user needs content ideas, wants to brainstorm articles, asks "what should I write about", or needs to fill content gaps. Use for "brainstorm", "topic ideas", "what to write", "content gaps", or "blog ideas". Do NOT use for writing posts, creating outlines, or SEO optimization without a specific ideation need.
Create a new voice profile from writing samples. 7-phase pipeline: Collect, Extract, Pattern, Rule, Generate, Validate, Iterate. Wabi-sabi (natural imperfections as features) is the core principle. Use when creating a new voice, starting voice calibration, or building a voice profile from scratch. Use for "create voice", "new voice", "build voice", "voice from samples", "calibrate voice". Do NOT use for generating content in an existing voice (use voice-orchestrator), editing content (use anti-ai-editor), or comparing voices (use voice-calibrator compare mode).
Generate headless Claude Code cron jobs from a task description and schedule. Creates a wrapper script with safety mechanisms (lockfile, budget cap, dry-run default, logging) and installs crontab entries via deterministic Python script. Use when user says "schedule", "run every", "cron job", "run twice daily", "run hourly", "run daily", "run weekly", or "schedule task".
Defense-in-depth verification before declaring any task complete. Run tests, check build, validate changed files, verify no regressions. Applies 4-level adversarial artifact verification (EXISTS > SUBSTANTIVE > WIRED > DATA FLOWS) with goal-backward framing. Use before saying "done", "fixed", or "complete" on any code change. Use for "verify", "make sure it works", "check before committing", or "validate changes". Do NOT use for debugging (use systematic-debugging) or code review (use systematic-code-review).
Interact with the learning system: show stats, list/search accumulated knowledge, and graduate mature entries into agents/skills. Backed by learning.db (SQLite + FTS5). Use when user says "retro", "retro list", "retro search", "retro graduate", "check knowledge", "what have we learned", "knowledge health", "graduate knowledge".
Review and revise content to remove AI-sounding patterns. Voice-agnostic editor that detects cliches, passive voice, structural monotony, and meta-commentary. Use when content sounds robotic, needs de-AIing, or voice validation flags synthetic patterns. Use for "edit for AI", "remove AI patterns", "make it sound human", or "de-AI this". Do NOT use for grammar checking, factual editing, or full rewrites. Do NOT use for voice generation (use voice skills instead).
Explicit anti-rationalization enforcement for maximum-rigor task execution. Loads all anti-rationalization patterns, gate enforcement, and pressure resistance as a composable modifier on any task. Use when executing critical production changes, security-sensitive code, complex multi-file refactors, or any task where shortcuts could cause harm. Use for "with rigor", "carefully", "maximum verification", or "no shortcuts". Do NOT use for trivial lookups, documentation-only edits, or simple typo fixes where full gate enforcement would be disproportionate overhead.
A/B test agent variants measuring quality and total session token cost across simple and complex benchmarks. Use when creating compact agent versions, validating agent changes, comparing internal vs external agents, or deciding between variants for production. Use for "compare agents", "A/B test", "benchmark agents", or "test agent efficiency". Do NOT use for evaluating single agents, testing skills, or optimizing prompts without variant comparison.
Guided Perses dashboard creation: gather requirements (metrics, datasource, layout), generate CUE definition or JSON spec, validate with percli lint, deploy with percli apply or MCP perses_create_dashboard. Use when user wants to create a new Perses dashboard, build a monitoring dashboard, or generate dashboard definitions. Use for "create perses dashboard", "new dashboard", "perses new dashboard", "build dashboard". Do NOT use for Grafana migration (use perses-grafana-migrate) or plugin development (use perses-plugin-create).
Deterministic 3-phase service health monitoring: Discover, Check, Report. Use when user asks about service status, process health, uptime, or whether services are running. Use for "health check", "is service up", "service status", "what's running", or "check if alive". Do NOT use for HTTP endpoint validation, performance profiling, or log analysis without a specific health concern.